M4 Pro (16-core GPU, 64 GB)

2 records across 2 models (quants: Q4_K - Medium).

hardwaremodelquantbackendtok/spp tok/sWttft sctx/tgdateclassflagssource
M4 Pro (16-core GPU, 64 GB)llama-3-2-1b-instruct Q4_K - Mediumllamafile111.935099222222221858.9418227777776–0.6703511943333332––sourced–source
M4 Pro (16-core GPU, 64 GB)qwen-2-5-14b-instruct Q4_K - Mediumllamafile16.132661555555554151.01082800000003–8.460523194444445––sourced–source

All rows cite their source. Provenance: community 40018 sourced 1085

← all hardware